Improving Explainable Object-induced Model through Uncertainty for Automated Vehicles

arXiv:2402.15572v1 Announce Type: cross
Abstract: The rapid evolution of automated vehicles (AVs) has the potential to provide safer, more efficient, and comfortable travel options. However, these systems face challenges regarding reliability in complex driving scenarios. Recent explainable AV architectures neglect crucial information related to inherent uncertainties while providing explanations for actions. To overcome such challenges, our study builds upon the "object-induced" model approach that prioritizes the role of objects in scenes for decision-making and integrates uncertainty assessment into the decision-making …

abstract architectures arxiv automated automated vehicles challenges cs.ai cs.cv cs.ro driving evolution face information reliability systems through travel type uncertainty vehicles